last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006654466810846781,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006654466810846781,
      "grad_norm": 0.10643411427736282,
      "learning_rate": 2e-05,
      "loss": 1.3965,
      "step": 1
    },
    {
      "epoch": 0.0013308933621693562,
      "grad_norm": 0.05983343347907066,
      "learning_rate": 4e-05,
      "loss": 1.2724,
      "step": 2
    },
    {
      "epoch": 0.001996340043254034,
      "grad_norm": 0.07062945514917374,
      "learning_rate": 6e-05,
      "loss": 1.5656,
      "step": 3
    },
    {
      "epoch": 0.001996340043254034,
      "eval_loss": 1.6909511089324951,
      "eval_runtime": 31.9291,
      "eval_samples_per_second": 19.825,
      "eval_steps_per_second": 9.928,
      "step": 3
    },
    {
      "epoch": 0.0026617867243387125,
      "grad_norm": 0.0796588733792305,
      "learning_rate": 8e-05,
      "loss": 1.6831,
      "step": 4
    },
    {
      "epoch": 0.0033272334054233904,
      "grad_norm": 0.05855264514684677,
      "learning_rate": 0.0001,
      "loss": 1.0757,
      "step": 5
    },
    {
      "epoch": 0.003992680086508068,
      "grad_norm": 0.0703502893447876,
      "learning_rate": 0.00012,
      "loss": 1.3986,
      "step": 6
    },
    {
      "epoch": 0.003992680086508068,
      "eval_loss": 1.6905368566513062,
      "eval_runtime": 32.1735,
      "eval_samples_per_second": 19.675,
      "eval_steps_per_second": 9.853,
      "step": 6
    },
    {
      "epoch": 0.004658126767592747,
      "grad_norm": 0.08330302685499191,
      "learning_rate": 0.00014,
      "loss": 1.8142,
      "step": 7
    },
    {
      "epoch": 0.005323573448677425,
      "grad_norm": 0.07740814238786697,
      "learning_rate": 0.00016,
      "loss": 1.4322,
      "step": 8
    },
    {
      "epoch": 0.005989020129762102,
      "grad_norm": 0.09462728351354599,
      "learning_rate": 0.00018,
      "loss": 1.4801,
      "step": 9
    },
    {
      "epoch": 0.005989020129762102,
      "eval_loss": 1.6890851259231567,
      "eval_runtime": 31.3841,
      "eval_samples_per_second": 20.169,
      "eval_steps_per_second": 10.101,
      "step": 9
    },
    {
      "epoch": 0.006654466810846781,
      "grad_norm": 0.0852142721414566,
      "learning_rate": 0.0002,
      "loss": 1.3184,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 117587666534400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}